检索增强神经场用于HRTF上采样与个性化
Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization
AI总结：
针对HRTF上采样仅依赖少量测量方向困难的问题，提出检索增强神经场（RANF），利用检索相似受试者的HRTF辅助神经场，在SONICOM数据集上验证有效性并助力赢得2024年个性化挑战赛。
摘要：
具有密集空间网格的头部相关传递函数（HRTFs）对于沉浸式双耳音频生成是理想的，但记录它们耗时。尽管神经场在HRTF空间上采样方面已取得显著进展，但仅从少数测量方向（例如3或5个测量）进行空间上采样仍然具有挑战性。为解决此问题，我们提出了一种检索增强神经场（RANF）。RANF从数据集中检索一个其HRTFs与目标受试者相近的受试者。除了声源方向本身，检索到的受试者在所需方向上的HRTF也被输入到神经场中。此外，我们提出了一种神经网络，能够高效处理多个检索到的受试者，灵感来自一种称为变换-平均-拼接的多通道处理技术。我们的实验在SONICOM数据集上证实了RANF的益处，并且它是2024年听者声学个性化挑战赛任务2获胜解决方案的关键组成部分。
英文摘要：
Head-related transfer functions (HRTFs) with dense spatial grids are desired for immersive binaural audio generation, but their recording is time-consuming. Although HRTF spatial upsampling has shown remarkable progress with neural fields, spatial upsampling only from a few measured directions, e.g., 3 or 5 measurements, is still challenging. To tackle this problem, we propose a retrieval-augmented neural field (RANF). RANF retrieves a subject whose HRTFs are close to those of the target subject from a dataset. The HRTF of the retrieved subject at the desired direction is fed into the neural field in addition to the sound source direction itself. Furthermore, we present a neural network that can efficiently handle multiple retrieved subjects, inspired by a multi-channel processing technique called transform-average-concatenate. Our experiments confirm the benefits of RANF on the SONICOM dataset, and it is a key component in the winning solution of Task 2 of the listener acoustic personalization challenge 2024.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
